Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    print, bool, player

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.39
     that
    0.36
     are
    0.34
    :
    0.33
     you
    0.32
     we
    0.32
     Đình
    0.31
    ificare
    0.31
    ",
    0.30
     la
    0.30
    POSITIVE LOGITS
    in
    0.58
    та
    0.52
    ون
    0.47
    ↵
    0.46
    л
    0.44
    و
    0.43
    og
    0.42
    ل
    0.42
    om
    0.40
    is
    0.40
    Act Density 0.784%

    No Known Activations